Mingze Wang
14 papers · 2022–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Cross-Pollinator (12) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Renaissance Researcher (7)
π
Renaissance Researcher
(7)
πΊοΈ
Taxonomy Completionist
(26)
π
Grand Slam
β‘
Prolific Year
(6)
π₯
Unstoppable
(5)
π
Century Club
(12)
ποΈ
Keyword Collector
(58)
β
The Questioner
Conferences
NIPS (6)
ICML (3)
AAAI (2)
ACL (2)
ICLR (1)
Top co-authors
Keywords
stochastic gradient descent
(4)
neural network optimization
(4)
sharpness-aware minimization
(2)
learning dynamics
(2)
neural network
(2)
implicit regularization
(2)
flat minima
(2)
attention mechanism
(1)
text classification
(1)
neural tangent kernel
(1)
neural network theory
(1)
stability analysis
(1)
label noise
(1)
reward function
(1)
adversarial perturbation
(1)
theoretical analysis
(1)
adversarial attack
(1)
expressive power
(1)
hessian matrix
(1)
spectral norm
(1)
Papers
CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
AAAI 2026
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
AAAI 2026
Tunable LLM-based Proactive Recommendation Agent
ACL 2025
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
ICLR 2025
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
ICML 2025
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
NIPS 2024
Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
ACL 2024
Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement
ICML 2024
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
NIPS 2024
Improving Generalization and Convergence by Enhancing Implicit Regularization
NIPS 2024
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
ICML 2024
Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks
NIPS 2023
Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks
NIPS 2022
The alignment property of SGD noise and how it helps select flat minima: A stability analysis
NIPS 2022